Design-development of an at-home modular brain-computer interface (BCI) platform in a case study of cervical spinal cord injury.
Kevin C Davis, Benyamin Meschede-Krasa, Iahn Cajigas and 14 others
PMID 35659259WHAT IT FOUND
In a person with cervical spinal cord injury, an implanted brain-to-glove system worked at home, with hand-grasp commands classified correctly 87.53% of the time over a year without recalibration.
This is feasibility, not proof of benefit.
Key findings
01One 22-year-old person with chronic cervical quadriplegia (C5 ASIA A) used a fully implanted brain-surface electrode (ECoG) at-home BCI platform to control a mechanical hand-grasp glove.
02The decoder was trained from 33 five-minute home data-collection trials, then tested in 17 trials without glove triggering and 12 trials with glove triggering, and remained stable over the next year without recalibration, with 87.53% correct classification across 79 trials.
03Setup from system start to neural control of the glove averaged 5.58 minutes, with 2.34 minutes for Bluetooth/app configuration and 2.18 minutes for donning the glove.
STILL TO COME
How it was doneWhat they foundWhat it means for OTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The implementation reports a single person, so it cannot show that the system works for other people with cervical spinal cord injury. There was no comparison group or controlled test of clinical benefit. User evaluation was not systematic, and the subject's comment about ease of use was not quantified. The app required residual bicep movement, which may limit use for people with less residual function. The external telemeter antenna had to be placed near the implanted generator, so the system was not completely wireless. The battery life of the implanted generator in this non-stimulation use was unknown. Only limited brain-surface electrode channels were used, which may restrict functional output compared with more channels.
Declared interests
The paper states that The Miami Project to Cure Paralysis funded the work. No other conflicts are stated.
The easy way to misread this
Do not read this as evidence that a brain-computer interface glove restores useful hand function in cervical spinal cord injury. It describes a single person and technical system performance, not a controlled clinical outcome.